Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification

• URL: http://arxiv.org/abs/2412.12782v1
• Date: Tue, 17 Dec 2024 10:42:19 GMT
• Title: Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification
• Authors: Zhiguang Lu, Qianqian Xu, Shilong Bao, Zhiyong Yang, Qingming Huang,
• Abstract summary: This paper addresses the challenge of Granularity Competition in fine-grained classification tasks. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder. We propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement.
• Score: 89.20477310885731
• License:
• Abstract: This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder. However, because coarse-grained levels are inherently easier to learn than finer ones, the base encoder tends to prioritize coarse feature abstractions, which impedes the learning of fine-grained features. To overcome this challenge, we propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement. The key idea is to develop classifiers sequentially from the finest to the coarsest granularities, rather than parallelly constructing a set of classifiers based on the same input features. In this setup, the outputs of finer-grained classifiers serve as inputs for coarser-grained ones, facilitating the flow of hierarchical semantic information across different granularities. On top of this, we further introduce an Adaptive Intra-Granularity Difference Learning (AIGDL) approach to uncover subtle semantic differences between classes within the same granularity. Extensive experiments demonstrate the effectiveness of our proposed method.

Related papers

• Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation [29.590172105562075]
  Class-Incremental Source-Free Unsupervised Domain Adaptation problem poses two challenges. We propose the Multi-Granularity Class Prototype Topology Distillation (GROTO) algorithm. Our proposed method achieves state-of-the-art performances on three public datasets.
  arXiv  Detail & Related papers  (2024-11-25T03:28:09Z)
• Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
  In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
  arXiv  Detail & Related papers  (2024-11-20T02:57:35Z)
• OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation [69.37484603556307]
  Un Semantic segmenting (USS) involves segmenting images without relying on predefined labels. We introduce a novel approach called Optimally Matched Hierarchy (OMH) to simultaneously address the above issues. Our OMH yields better unsupervised segmentation performance compared to existing USS methods.
  arXiv  Detail & Related papers  (2024-03-11T09:46:41Z)
• Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation [34.257289290796315]
  We propose the Relevant Intrinsic Feature Enhancement Network (RiFeNet) to improve semantic consistency of foreground instances. RiFeNet surpasses the state-of-the-art methods on PASCAL-5i and COCO benchmarks.
  arXiv  Detail & Related papers  (2023-12-11T16:02:57Z)
• Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels [43.3561344548331]
  We propose a method that embeds visual embeddings into a hyperbolic space and enhances their discriminative ability with a hierarchical cosine margins manner. Specifically, the hyperbolic space offers distinct advantages, including the ability to capture hierarchical relationships. Based on the hyperbolic space, we further enforce relatively large/small similarity margins between coarse/fine classes, respectively, yielding the so-called hierarchical cosine margins manner.
  arXiv  Detail & Related papers  (2023-11-18T09:42:03Z)
• Dynamic Perceiver for Efficient Visual Recognition [87.08210214417309]
  We propose Dynamic Perceiver (Dyn-Perceiver) to decouple the feature extraction procedure and the early classification task. A feature branch serves to extract image features, while a classification branch processes a latent code assigned for classification tasks. Early exits are placed exclusively within the classification branch, thus eliminating the need for linear separability in low-level features.
  arXiv  Detail & Related papers  (2023-06-20T03:00:22Z)
• The Overlooked Classifier in Human-Object Interaction Recognition [82.20671129356037]
  We encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs. We propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset. Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin.
  arXiv  Detail & Related papers  (2022-03-10T23:35:00Z)
• Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding [13.063136901934865]
  Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time. In this paper, we advance the few-shot classification paradigm towards a more challenging scenario, i.e., cross-granularity few-shot classification. We approximate the fine-grained data distribution by greedy clustering of each coarse-class into pseudo-fine-classes according to the similarity of image embeddings.
  arXiv  Detail & Related papers  (2020-07-11T03:44:21Z)
• Semi-Supervised Semantic Segmentation with Cross-Consistency Training [8.894935073145252]
  We present a novel cross-consistency based semi-supervised approach for semantic segmentation. Our method achieves state-of-the-art results in several datasets.
  arXiv  Detail & Related papers  (2020-03-19T20:10:37Z)
• Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches [67.51747235117]
  Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks. Recent works mainly tackle this problem by focusing on how to locate the most discriminative parts. We propose a novel framework for fine-grained visual classification to tackle these problems.
  arXiv  Detail & Related papers  (2020-03-08T19:27:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.